Image Object Detection Model for Random Sample Images Using TensorFlow Take 3

David Lowe

November 3, 2021

Template Credit: Adapted from an Object Detection tutorial on TensorFlow.org.

Additional Notes: I adapted this workflow from the TensorFlow Object Detection tutorial on TensorFlow.org (https://www.tensorflow.org/hub/tutorials/object_detection). I plan to build a script for building future projects using object detection models.

SUMMARY: This project aims to construct an object detection model using the TensorFlow-based neural network and document the end-to-end steps using a template.

This iteration will use the TF2 CenterNet HourGlass104 1024x1024 object detection model to test some sample images. The model was constructed using the CenterNet Object detection model with the Hourglass backbone and trained on COCO 2017 dataset with training images scaled to 1024x1024.

Original Script Location: https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/tf2_object_detection.ipynb

Images Used: See project code below

Dataset ML Model: Image Object Detection using TensorFlow Hub Models

Additional References: https://tfhub.dev/s?module-type=image-object-detection

Task 1 - Prepare Environment

Task 2 - Set up Visualization and Helper Functions

Task 3 - Prepare and Load Model

Task 4 - Load Images and Apply Model